{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7F6LL5FHG2T2YPMWYW5CP3X3U2","short_pith_number":"pith:7F6LL5FH","schema_version":"1.0","canonical_sha256":"f97cb5f4a736a7ac3d96c5ba27eefba6a10c2a190f9125d14ab86640d7ab7dc2","source":{"kind":"arxiv","id":"2412.05980","version":1},"attestation_state":"computed","paper":{"title":"Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai Ci, Jiaming Liu, Mike Zheng Shou, Pei Yang, Shengtao Lou, Xiaokang Liu, Yiren Song","submitted_at":"2024-12-08T16:04:45Z","abstract_excerpt":"Diffusion models have revolutionized generative modeling with their exceptional ability to produce high-fidelity images. However, misuse of such potent tools can lead to the creation of fake news or disturbing content targeting individuals, resulting in significant social harm. In this paper, we introduce Anti-Reference, a novel method that protects images from the threats posed by reference-based generation techniques by adding imperceptible adversarial noise to the images. We propose a unified loss function that enables joint attacks on fine-tuning-based customization methods, non-fine-tunin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.05980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T16:04:45Z","cross_cats_sorted":[],"title_canon_sha256":"d12f66f32074fdd0612d9e387d6559cc7f3496690e6f19f622de90ef4412fb3c","abstract_canon_sha256":"c7f953c5178219b54945ba193bc8cc387f2ab170b1312b47d4077162b090ccf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:12.553216Z","signature_b64":"+lWa2ldF5jGwHYdqNa3Eh+cNnHTf9CdkY+pGWngekGSs+yKQBMmtfaZdd9libFf9OhumrnbLwrrFV+Ev6fUqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f97cb5f4a736a7ac3d96c5ba27eefba6a10c2a190f9125d14ab86640d7ab7dc2","last_reissued_at":"2026-07-05T09:46:12.552769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:12.552769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai Ci, Jiaming Liu, Mike Zheng Shou, Pei Yang, Shengtao Lou, Xiaokang Liu, Yiren Song","submitted_at":"2024-12-08T16:04:45Z","abstract_excerpt":"Diffusion models have revolutionized generative modeling with their exceptional ability to produce high-fidelity images. However, misuse of such potent tools can lead to the creation of fake news or disturbing content targeting individuals, resulting in significant social harm. In this paper, we introduce Anti-Reference, a novel method that protects images from the threats posed by reference-based generation techniques by adding imperceptible adversarial noise to the images. We propose a unified loss function that enables joint attacks on fine-tuning-based customization methods, non-fine-tunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05980","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.05980/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.05980","created_at":"2026-07-05T09:46:12.552834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05980v1","created_at":"2026-07-05T09:46:12.552834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05980","created_at":"2026-07-05T09:46:12.552834+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F6LL5FHG2T2","created_at":"2026-07-05T09:46:12.552834+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F6LL5FHG2T2YPMW","created_at":"2026-07-05T09:46:12.552834+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F6LL5FH","created_at":"2026-07-05T09:46:12.552834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02528","citing_title":"RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2","json":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2.json","graph_json":"https://pith.science/api/pith-number/7F6LL5FHG2T2YPMWYW5CP3X3U2/graph.json","events_json":"https://pith.science/api/pith-number/7F6LL5FHG2T2YPMWYW5CP3X3U2/events.json","paper":"https://pith.science/paper/7F6LL5FH"},"agent_actions":{"view_html":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2","download_json":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2.json","view_paper":"https://pith.science/paper/7F6LL5FH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05980&json=true","fetch_graph":"https://pith.science/api/pith-number/7F6LL5FHG2T2YPMWYW5CP3X3U2/graph.json","fetch_events":"https://pith.science/api/pith-number/7F6LL5FHG2T2YPMWYW5CP3X3U2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2/action/storage_attestation","attest_author":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2/action/author_attestation","sign_citation":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2/action/citation_signature","submit_replication":"https://pith.science/pith/7F6LL5FHG2T2YPMWYW5CP3X3U2/action/replication_record"}},"created_at":"2026-07-05T09:46:12.552834+00:00","updated_at":"2026-07-05T09:46:12.552834+00:00"}